Get 3D scene using 3D Gaussian splatting with neural signed distance fields with GSDF
Get 3D scene using 3D Gaussian splatting with neural signed distance fields with GSDF
GSDF: 3DGS Meets SDF for Improved Rendering and Reconstruction
arXiv paper abstract https://arxiv.org/abs/2403.16964
arXiv PDF paper https://arxiv.org/pdf/2403.16964.pdf
Project page https://city-super.github.io/GSDF
Presenting a 3D scene from multiview images remains a core and long-standing challenge in computer vision and computer graphics.
... rendering ... usually achieved with neural volumetric rendering ... neglect the underlying scene geometry. Learning of neural implicit surfaces is ... from the success of neural rendering.
Current works either constrain the distribution of density fields or the shape of primitives, resulting in degraded rendering quality and flaws on the learned scene surfaces.
... introduce GSDF, a novel dual-branch architecture that combines the benefits of a flexible and efficient 3D Gaussian Splatting (3DGS) representation with neural Signed Distance Fields (SDF).
The core idea is to leverage and enhance the strengths of each branch while alleviating their limitation through mutual guidance and joint supervision.
... show on diverse scenes ... more accurate and detailed surface reconstructions, and ... benefits 3DGS rendering ... more aligned with ... geometry.
Please like and share this post if you enjoyed it using the buttons at the bottom!
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
